harnesslab
PulseGate's liveness check found it on 22 Sep 2026; it is registered on GitHub and PyPI and has been in the index since 22 Sep 2026. How this is checked
Harnesslab is a local-first experimentation platform for evaluating AI coding-agent harnesses. It runs the same tasks in isolated worktrees, applies an independent verifier, and records normalized traces to compare verified configurations and cost.
Inferred · not functionally tested
Overview
6 featuresPurpose: Comparing AI coding-agent harnesses consistently without relying on shared state or unverified results.
Inferred · not functionally tested
Audience: AI developer-tool researchers and engineers
Inferred · not functionally tested
Functions: analytics, monitoring
Inferred · not functionally tested
Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: pypi.org · github.com. These links do not verify the individual claims.
harnesslab is an Agent evaluation & testing project. Inferred · not functionally tested: It focuses on comparing AI coding-agent harnesses consistently without relying on shared state or unverified results. Inferred · not functionally tested: It is built as an open-source project for AI developer-tool researchers and engineers. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: harnesslab is available on the command line, and it can be self-hosted.
Behind harnesslab is Bilgin Koçak, and it first shipped in 2026. The project is developed in the open on GitHub with 5 commits in the last 90 days. Inferred · not functionally tested: Key capabilities include task benchmarking, isolated worktrees, and independent verification.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Task benchmarking
- Isolated worktrees
- Independent verification
- Trace normalization
- Configuration comparison
- Cost comparison
Topics: Inferred · not functionally tested
Built with & integrations
- Claude Code
- commit 3bcda187469e · since Sep 2026
Trust & compliance
Indexing history
2What PulseGate has recorded for this listing
- Indexed22 Sep · 20:26 UTCharnesslab seen via PyPI Bulk EnumeratorSource: PyPI Bulk Enumerator · Open
Frequently asked questions about harnesslab
- What does harnesslab do?
- Inferred · not functionally tested: Harnesslab focuses on comparing AI coding-agent harnesses consistently without relying on shared state or unverified results. It is catalogued under Agent evaluation & testing on PulseGate.
- Who is harnesslab for?
- Inferred · not functionally tested: harnesslab is an open-source project built for AI developer-tool researchers and engineers.
- Does harnesslab have a free plan?
- Basis unknown · not verified: Yes — harnesslab is open source under the MIT license and free to use.
- What platforms does harnesslab run on?
- Basis unknown · not verified: harnesslab runs on the command line. It can also be self-hosted.
- Is harnesslab still active?
- PulseGate's liveness check found it on 22 Sep 2026. Its GitHub repository shows 5 commits in the last 90 days.
- What projects are similar to harnesslab?
- Similar projects tracked by PulseGate include warrantor-harness, diy-harness, and harnessgym.warrantor-harnessdiy-harnessharnessgym
- Who makes harnesslab?
- harnesslab is developed by Bilgin Koçak.
- How long has harnesslab been around?
- harnesslab first shipped in 2026.
Similar projects
Closest matches by what these projects do